---
title: 'DehazeSB: Segmentation & SB Dehazing'
url: https://www.emergentmind.com/topics/dehazesb
type: topic
---

# DehazeSB: Segmentation & SB Dehazing

DehazeSB refers to several distinct, technically advanced image dehazing methods and frameworks whose shared designation arises from segmentation- or Schrödinger Bridge-based approaches. These systems are characterized by either explicit sky-region segmentation, integration of large-scale segmentation priors, or optimal transport via Schrödinger Bridge theory, and have each contributed significant advances in real-world image dehazing under challenging, unpaired, or low-data regimes [2507.09524, 2007.06492, 2306.15870]. This entry systematically details all primary DehazeSB variants, their theoretical formulations, algorithmic structures, and quantitative benchmarks.

## 1. Sky/Non-Sky Segmentation Hybrid (DehazeSB, 2020)

One foundational approach labeled DehazeSB is the two-stage hybrid system combining region segmentation and region-adaptive dehazing [2007.06492]. The method centers on decomposing the input image into sky and non-sky regions for specialized treatment.

### Algorithmic Pipeline

- **Stage I: Sky/Non-Sky Segmentation**
    - The input image \(I(x)\) is first segmented using edge detection with confidence weighting and MeanShift clustering in the spatial–color domain.
    - Morphological post-processing yields a binary sky mask \(M_{\text{sky}}(x)\).

- **Stage II: Region-Adaptive Dehazing**
    - **Non-sky regions**: Dehazed by an improved Dark Channel Prior (DCP), which substitutes the local minimum with a local average to mitigate haze overestimation:
      \[
      \tilde{D}(x) = \frac{1}{|\Omega(x)|} \sum_{y \in \Omega(x)} \min_{c \in \{r,g,b\}} I^c(y)
      \]
      Raw transmission is:
      \[
      \hat{t}(x) = 1 - \omega \frac{\tilde{D}(x)}{A}
      \]
      with \(\omega=0.95\), further refined by guided filtering.
      Scene radiance is recovered via:
      \[
      J_{\text{non-sky}}(x) = \frac{I(x)-A}{\max(\hat{t}(x), t_0)} + A
      \]
      and adjusted for mean brightness.

    - **Sky regions**: Processed by an enhanced DehazeNet convolutional neural network comprising multi-scale feature blocks and PReLU activations.

    - **Fusion**: Output image is
      \[
      J(x) = M_{\text{sky}}(x) \cdot J_{\text{sky}}(x) + (1 - M_{\text{sky}}(x)) \cdot J_{\text{non-sky}}(x)
      \]

### Quantitative Performance

The DehazeSB segmentation hybrid achieves higher entropy, improved edge visibility, and reduced saturation artefacts versus He et al. (DCP) and Cai et al. (DehazeNet), with runtime \(2-3\,\mathrm{s}\) for \(473 \times 283\) images [2007.06492].

| Method      | Entropy↑ | VisRatio↑ | AvgGrad↑ | Sat%↓ | Time (s) |
|-------------|----------|-----------|----------|-------|----------|
| He et al.   | 5.7130   | 0.1146    | 3.6574   | 32.29 | 3.15     |
| Cai et al.  | —        | —         | —        | —     | —        |
| DehazeSB    | 5.7706   | 0.2492    | 4.0763   | 12.96 | 2.20     |

This variant addresses colour distortion in sky regions and improves gradient-based perceptual quality.

## 2. Segmentation-Boosted Dehazing with Large-Model Priors

A second major line designates DehazeSB as "Dehazing with Segmentation Boost," which exploits large-scale segmentation (SAM) priors for fine-grained, region-aware restoration [2306.15870].

### System Architecture

- **Segmentation-Aided Module:** The pipeline uses an off-the-shelf, frozen Segment Anything Model (SAM), producing a multi-instance object mask \(M_{\text{raw}}\) for each scene.
- **Grayscale Coding:** A coding mechanism compresses k-way masks into an 8-bit grayscale channel without index loss.
- **Channel-Expansion Block:** Input \(I\) and coded mask \(M\) are concatenated and projected to 64 feature channels through \(3 \times 3\) convolution, batch normalization, and ReLU.
- **Dehaze Network:** A U-Net backbone with multi-scale segmentation/feature fusion:
  \[
  F^{(i)}_{\text{fuse}} = \sigma(W_f [F^{(i)}_{\text{seg}}, F^{(i)}_{\text{vis}}])
  \]
- **Optional Pre-Dehaze:** Running a preliminary dehazer before segmentation further improves performance under dense haze.

### Training and Performance

The method is trained using an L1 reconstruction loss. Training is accelerated (30–40% fewer epochs) with mask priors. Quantitative gains shown below (PSNR/SSIM on NTIRE2020):

| Method         | PSNR (dB) | SSIM  |
|----------------|-----------|-------|
| DehazeNet      | 18.4      | 0.62  |
| AOD-Net        | 18.9      | 0.64  |
| Dehazeformer   | 19.8      | 0.65  |
| C2PNet         | 20.0      | 0.66  |
| **DehazeSB**   | **20.69** | **0.659** |

The performance benefits are most salient under medium or severe haze benchmarks [2306.15870].

## 3. Schrödinger Bridge-Based Unpaired Dehazing

The 2025 DehazeSB system is based on Schrödinger Bridge (SB) theory, addressing the fundamental bottleneck of unpaired dehazing via stochastic optimal transport [2507.09524]. 

### Theoretical Foundation

- **Schrödinger Bridge Problem:** Given source and target distributions \(\pi_0\), \(\pi_1\) (hazy and clear), seeks probability law \(\mathcal{Q}^{SB}\) minimizing KL divergence to a reference Wiener measure, subject to endpoint marginals:
  \[
  \mathcal{Q}^{SB} = \arg\min_{\mathcal{Q}} D_{KL}(\mathcal{Q}\;\|\;\mathcal{W}) \quad \text{ s.t. } \mathcal{Q}_{t=0}=\pi_0, \; \mathcal{Q}_{t=1} = \pi_1
  \]
  Leading to an entropy-regularized OT problem.

- **Neural Transport:** Discretization into \(N=5\) steps; generator \(G_\theta\) predicts final clear image given intermediate state, and intermediate samples are drawn conditionally using the SB tractable Gaussian.

### Loss Terms

- **Adversarial Loss:** Patch-level Markovian and CLIP-based discriminators for local and global distribution matching.
- **Detail-Preserving Regularization:**
    - PatchNCE (contrastive, deep feature) loss.
    - Physical prior (ASM-consistent) reconstruction loss.
    - High-frequency preservations: DFT, SSIM, and Sobel gradient matching.
- **Prompt Learning with CLIP:** Learns a haze-reflecting embedding \(T_{\text{hazy}}\), enforcing distance of dehazed outputs from "hazy" semantics.

### Training and Results

SB-based DehazeSB achieves state-of-the-art FID, NIQE, and perceptual scores on real-world unpaired datasets; e.g., on OHAZE: PSNR=18.83 dB, SSIM=0.838, VSI=0.961. Ablations confirm each regularization is necessary for optimal balance of detail, contrast, and artifact suppression [2507.09524].

## 4. Comparative Evaluations

Cross-publication benchmarks indicate that DehazeSB approaches yield improved or competitive results compared to prior state-of-the-art, particularly under dense or non-uniform haze. Direct comparisons (PSNR/SSIM, FID, NIQE, etc.) are presented in each respective paper, with the methods generally excelling on perceptual structure, entropy, and convergence speed.

| DehazeSB Variant              | Key Mechanism             | Principal Benchmark Leader |
|-------------------------------|---------------------------|---------------------------|
| Sky segmentation hybrid [2007.06492] | Edge + MeanShift + CNN       | Gradient/entropy/fusion   |
| SAM segmentation-boost [2306.15870]  | Large-segmentation prior     | PSNR/SSIM/hard fog        |
| Schrödinger Bridge [2507.09524]      | Stochastic optimal transport | FID/MUSIQ/no-ref metrics  |

## 5. Current Limitations and Design Insights

Analyses across all three DehazeSB families point to several limitations and open questions:

- **Overfitting to Haze Distribution:** Learned prompt embeddings (SB variant) may be over-specialized if haze types in training are insufficiently varied [2507.09524].
- **Extreme Haze Cases:** All methods exhibit some degradation under extremely dense haze, particularly in fine texture recovery [2507.09524].
- **Architectural Choices:** In the segmentation-boosted pipeline, pre-dehaze modules and multi-scale fusion most benefit scenarios with heavy and non-uniform fog [2306.15870].
- **Absence of Fine-Tuning:** Off-the-shelf segmentors/SAM can transfer well without additional optimization, contributing to generalization and faster training [2306.15870].

## 6. Significance in Dehazing Research

DehazeSB methodologies represent the convergence of domain-aware segmentation, neural optimal transport, and the use of large vision-language priors within efficient or lightweight architectures. Their adoption in both paired and unpaired scenarios, across synthetic and real datasets, illustrates the field's shift toward hybrid, data- and prior-efficient models robust to data gaps and challenging haze conditions [2507.09524, 2306.15870, 2007.06492]. Each approach provides modular advances—segmentation fusion, region-adaptive CNNs, stochastic-OT regularization—that inform subsequent design in image restoration and generative modeling.

Source: https://www.emergentmind.com/topics/dehazesb